puppeteer_hover · MCP-pptr MCP: Risk & Policy

WHAT IT DOES

What puppeteer_hover does on MCP-pptr

AI agents invoke puppeteer_hover to trigger actions in MCP-pptr. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why puppeteer_hover needs a policy

puppeteer_hover executes a browser interaction (hover event) that can trigger side effects through event handlers, CSS pseudo-states, or JavaScript callbacks. While not destructive or financial, it modifies the runtime state of a webpage and can cause observable changes or execute code. This fits the Execute category: it runs a browser action whose effects depend on what handlers are attached to the hovered element.

From the tool's definition Tool name: puppeteer_hover. Description: 'Hover an element on the page.' This is a browser automation action that triggers DOM events and may invoke JavaScript handlers on hover.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_hover Rate-limited

puppeteer_hover stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "puppeteer_hover": {
      "limits": [
        {
          "counter": "puppeteer_hover_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP-pptr, so you can run agents against it safely.

FAQ

Questions about puppeteer_hover

What does the puppeteer_hover tool do? +

Hover an element on the page. It is categorised as a Execute tool in the MCP-pptr MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on puppeteer_hover? +

Register the MCP-pptr MCP server in PolicyLayer and add a rule for puppeteer_hover: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP-pptr. Nothing to install.

What risk level is puppeteer_hover? +

puppeteer_hover is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit puppeteer_hover? +

Yes. Add a rate_limit block to the puppeteer_hover rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block puppeteer_hover completely? +

Set action: deny in the PolicyLayer policy for puppeteer_hover. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides puppeteer_hover? +

puppeteer_hover is provided by the MCP-pptr MCP server (ringotc/mcp-pptr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.